watchFiles

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already include readOnlyHint=true, indicating the tool does not modify state. The description adds context about watching file changes, which aligns with read-only behavior. No deeper behavioral details are given (e.g., how events are delivered), but the annotations already cover the safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise with two well-structured sentences. The first sentence states the core action, and the second references the sibling tool for stopping. No unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple watch tool with two parameters and no output schema, the description covers the basic purpose and the counterpart tool. However, it lacks details on how the results are delivered (e.g., events, callbacks, or streaming). This is a gap that could affect an agent's ability to handle the tool's output correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the input schema fully describes the two parameters (id and pattern). The description mentions 'glob pattern', which mirrors the pattern parameter's description, but adds no new semantic information beyond what the schema provides. Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool watches a glob pattern for file changes (created/modified/deleted). It distinguishes from the sibling tool 'unwatchFiles' by mentioning it as the stop counterpart. The purpose is specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool (to watch file changes) and explicitly mentions the alternative 'unwatchFiles' to stop. However, it does not elaborate on when not to use it or compare to other watch-related siblings like watchActivityLog.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.